Name processing scripts

		Find name...		11,106,374 NameBank Records

Name processing scripts Tools/Algorithms

FindIt: Name recognition algorithm FindIt locates scientific name and authority information in HTML, XML, PDF, and Word documents. It uses a combination of rulesets and lexicons to provide a confidence ranking of all names within documents. A training component allows the rules and lexicon to be modified dynamically. A SOAP method allows findIT to be used as a component in external applications.	help
LinkIt: Name linking tool LinkIt locates scientific names in web output and redisplays the output with the names linked to any of a number of authority lists. A large number of output options allow the display to be controlled	help
Name canonization function This function takes a complex scientific name containing authorship and/or nomenclatural annotation and returns the basic canonical form of the name. Useful for comparing different forms of the same name for nominal equivalence	help
Name parser This function takes a complex scientific name and parses it into a string-indexed array identifying the different name, nomenclatural and authority components	help
Scientific name suffix analyzer A table that summarizes a lexical analysis of the suffixes of over 300,000 distinct genera names and over 400,000 distinct species epithets. These statistics are used within name recognition algorithms.	help
Checklist parser This application parses various standard checklist formats into a single normalized form.	help
MRIB Name Crawler This application crawls through a web site and uses the name recognition algorithm to locate all names within the site. Developed for the USGS Marine Realms Information Bank program.
Name Crawler with Classification tools This application crawls through a web site, identifies all names and stores their source location, and then reconciles all names to one or more authoritative classifications which can then be used to browse the files. (version 2)

(All tools are currently in development)